The evolution of Artificial Intelligence (AI) has reached a critical point, where agentic AI systems demonstrate strong capabilities in goal formulation and planning but remain difficult to deploy in real-world settings due to their limited grounding in physical environments. These limitations arise from the challenges of partial observability, actuation uncertainty, and strict resource constraints that characterize the physical world. This survey argues that the Artificial Intelligence of Things (AIoT) provides the necessary foundation to embed agentic intelligence into such environments by enabling continuous interaction between sensing, reasoning, and action. We analyze the synergy between goal-driven agentic AI and distributed AIoT infrastructures and present a unified taxonomy of AIoT-enabled agentic architectures, highlighting trade-offs across centralized, edge-native, and hybrid deployment models. The survey further examines key enabling technologies, including edge intelligence, semantic communication, digital twins, and trust mechanisms, and discusses how they integrate into cognitive control loops. Through representative applications in smart cities, industrial automation, healthcare, and energy systems, we show how this convergence moves automation beyond rule-based behavior toward context-aware autonomy. Finally, we identify open challenges related to long-horizon safety, resource-aware intelligence, and ethical governance, and outline research directions toward robust, trustworthy, and socially embedded autonomous systems.

The meteorological communication networks provide critical data support for agriculture and environmental monitoring. However, covert gradient-based attacks persistently inject subtle perturbations, threatening data integrity and increasing the operational overhead for network operators. To achieve proactive service assurance and security-aware network management, this paper proposes a data integrity monitoring mechanism as a managed network function, named EK-IGNN. Unlike traditional passive detection, EK-IGNN functions as an active security service. It first employs the Empirical Mode Decomposition Kalman Filter (EMD-KF) to extract high-fidelity attack fingerprints, which are then analyzed by an Intrinsic Graph Neural Network (IGNN). The IGNN model captures complex dependencies and adaptively amplifies weak attack features, enabling closed-loop network security management. Experimental results demonstrate that the proposed algorithm achieving an average improvement of 16.07% in accuracy and 15.27% in F1-score over state-of-the-art benchmarks.

Predicting remaining useful life (RUL) plays a crucial role in the prognostics and health management of industrial systems that involve a variety of interrelated sensors. Given a constant stream of time-series sensory data from such systems, deep learning (DL) models have risen to prominence at identifying complex, nonlinear temporal dependencies in these data. In addition to the temporal dependencies of individual sensors, spatial dependencies emerge as important correlations among these sensors, which can be naturally modeled by a temporal graph that describes time-varying spatial relationships. However, the majority of existing studies have relied on capturing discrete snapshots of this temporal graph, a coarse-grained approach that leads to a loss of temporal information. Moreover, given the variety of heterogeneous sensors, it becomes vital that such inherent heterogeneity is leveraged for RUL prediction in temporal sensor graphs. To capture the nuances of the temporal and spatial relationships and heterogeneous characteristics in an interconnected graph of sensors, we introduce a novel model named temporal and heterogeneous graph neural networks (THGNNs). Specifically, THGNN aggregates historical data from neighboring nodes to accurately capture the temporal dynamics and spatial correlations within the stream of sensor data in a fine-grained manner. Moreover, the model leverages feature-wise linear modulation (FiLM) to address the diversity of sensor types, significantly improving the model's capacity to learn the heterogeneity in the data sources. Finally, we have validated the effectiveness of our approach through comprehensive experiments. Our empirical findings demonstrate significant advancements on the N-CMAPSS dataset, achieving improvements of up to 19.2% and 31.6% in terms of two different evaluation metrics over state-of-the-art methods.

With the rapid development of Internet of Vehicles technology, mobile communications are gradually integrated with various fields, and more and more Internet of Vehicles equipment are connected to the Internet. However, existing online information transmission methods mainly rely on the original network infrastructure. Once the communication infrastructure fails, it is likely that information transmission will fail or even be lost. In this paper, we utilize the optical modules that come with sensor nodes to implement a hybrid communication debugging system based on Visible Light Communication (VLC). To enhance uplink reliability, we’ve devised an optical camera-compatible frame synchronization method. Leveraging the Transformer algorithm, we predict frame header positions, thereby bolstering data collection reliability. Additionally, for efficient debugging information uploading, we logically group and organize the initial data, and use the Snappy compression algorithm to decrease empty time slot count to complete the data compression, saving time. Finally, confidentiality enhancement technology is introduced in the physical layer, and a new security enhancement optimization scheme based on Artificial Noise is proposed. The Artificial Noise (AN) sent by the sender enables the sender to counter eavesdropping interference, and the authorized recipient can cancel the Artificial Noise (AN). The results show that the proposed scheme is more secure.

Medical dialogue models predominantly emphasize generating coherent and clinically accurate responses. However, in many clinical scenarios, time plays a pivotal role, often dictating subsequent patient management and interventions. Recognizing the latent importance of temporal dynamics, this paper introduces a novel dimension to medical dialogues: timestamps. We advocate that the integration of time-sensitive directives can profoundly impact medical advice, using an illustrative example of post-surgery care with and without timestamps. Our contributions are three-fold: Firstly, we highlight the intrinsic significance of timestamps in medical conversations, marking a paradigm shift in dialogue modeling. Secondly, we present an innovative dataset and framework explicitly tailored for time-stamped medical dialogues, facilitating the model to not only provide medical counsel but also chronologically outline care regimens. Lastly, empirical evaluations indicate our method's proficiency in time-stamped tasks and reveal an uptick in performance in broader medical Q&A domains. Through our endeavors, we aspire to set new benchmarks in patient-centric and time-sensitive medical dialogue systems.

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with no or few labeled samples, presents a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) to address low-resource text classification in a two-pronged approach. During pre-training, we propose three graph interaction-based contrastive strategies to jointly pre-train a graph-text model; during downstream classification, we explore handcrafted discrete prompts and continuous prompt tuning for the jointly pre-trained model to achieve zero- and few-shot classification, respectively. Moreover, we explore the possibility of employing continuous prompt tuning for zero-shot inference. Specifically, we aim to generalize continuous prompts to unseen classes while leveraging a set of base classes. To this end, we extend G2P2 into G2P2$^*$, hinging on a new architecture of conditional prompt tuning. Extensive experiments on four real-world datasets demonstrate the strength of G2P2 in zero- and few-shot low-resource text classification tasks, and illustrate the advantage of G2P2$^*$in dealing with unseen classes.

Large language models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawback of LLMs is the issue of hallucination, where they generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. In this paper, we propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers. RelD is trained on the constructed RelQA, a bilingual question-answering dialogue dataset along with answers generated by LLMs and a comprehensive set of metrics. Our experimental results demonstrate that the proposed RelD successfully detects hallucination in the answers generated by diverse LLMs. Moreover, it performs well in distinguishing hallucination in LLMs' generated answers from both in-distribution and out-of-distribution datasets. Additionally, we also conduct a thorough analysis of the types of hallucinations that occur and present valuable insights. This research significantly contributes to the detection of reliable answers generated by LLMs and holds noteworthy implications for mitigating hallucination in the future work.

Voucher abuse detection is an important anomaly detection problem in E-commerce. While many GNN-based solutions have emerged, the supervised paradigm depends on a large quantity of labeled data. A popular alternative is to adopt self-supervised pre-training using label-free data, and further fine-tune on a downstream task with limited labels. Nevertheless, the "pre-train, fine-tune" paradigm is often plagued by the objective gap between pre-training and downstream tasks. Hence, we propose VPGNN, a prompt-based fine-tuning framework on GNNs for voucher abuse detection. We design a novel graph prompting function to reformulate the downstream task into a similar template as the pretext task in pre-training, thereby narrowing the objective gap. Extensive experiments on both proprietary and public datasets demonstrate the strength of VPGNN in both few-shot and semi-supervised scenarios. Moreover, an online deployment of VPGNN in a production environment shows a 23.4% improvement over two existing deployed models.

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with few or no labeled samples, poses a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) to address low-resource text classification in a two-pronged approach. During pre-training, we propose three graph interaction-based contrastive strategies to jointly pre-train a graph-text model; during downstream classification, we explore prompting for the jointly pre-trained model to achieve low-resource classification. Extensive experiments on four real-world datasets demonstrate the strength of G2P2 in zero- and few-shot low-resource text classification tasks

Graph-structured data widely exist in diverse real-world scenarios, analysis of these graphs can uncover valuable insights about their respective application domains. However, most previous works focused on learning node representation from a single fixed graph, while many real-world scenarios require representations to be quickly generated for unseen nodes, new edges, or entirely new graphs. This inductive ability is essential for high-throughtput machine learning systems. However, this inductive graph representation problem is quite difficult, compared to the transductive setting, for that generalizing to unseen nodes requires new subgraphs containing the new nodes to be aligned to the neural network trained already. Meanwhile, following a message passing framework, graphneural network (GNN) is an inductive and powerful graph representation tool. We further explore inductive GNN from more specific perspectives: (1) generalizing GNN across graphs, in which we tackle with the problem of semi-supervised node classification across graphs; (2) generalizing GNN across time, in which we mainly solve the problem of temporal link prediction; (3) generalizing GNN across tasks; (4) generalizing GNN across locations.

Temporal graph representation learning has drawn significant attention for the prevalence of temporal graphs in the real world. However, most existing works resort to taking discrete snapshots of the temporal graph, or are not inductive to deal with new nodes, or do not model the exciting effects which is the ability of events to influence the occurrence of another event. In this work, We propose TREND, a novel framework for temporal graph representation learning, driven by TempoRal Event and Node Dynamics and built upon a Hawkes process-based graph neural network (GNN). TREND presents a few major advantages: (1) it is inductive due to its GNN architecture; (2) it captures the exciting effects between events by the adoption of the Hawkes process; (3) as our main novelty, it captures the individual and collective characteristics of events by integrating both event and node dynamics, driving a more precise modeling of the temporal process. Extensive experiments on four real-world datasets demonstrate the effectiveness of our proposed model.

Semi-supervised node classification on graphs is an important research problem, with many real-world applications in information retrieval such as content classification on a social network and query intent classification on an e-commerce query graph. While traditional approaches are largely transductive, recent graph neural networks (GNNs) integrate node features with network structures, thus enabling inductive node classification models that can be applied to new nodes or even new graphs in the same feature space. However, inter-graph differences still exist across graphs within the same domain. Thus, training just one global model (e.g., a state-of-the-art GNN) to handle all new graphs, whilst ignoring the inter-graph differences, can lead to suboptimal performance. In this paper, we study the problem of inductive node classification across graphs. Unlike existing one-model-fits-all approaches, we propose a novel meta-inductive framework called MI-GNN to customize the inductive model to each graph under a meta-learning paradigm. That is, MI-GNN does not directly learn an inductive model; it learns the general knowledge of how to train a model for semi-supervised node classification on new graphs. To cope with the differences across graphs, MI-GNN employs a dual adaptation mechanism at both the graph and task levels. More specifically, we learn a graph prior to adapt for the graph-level differences, and a task prior to adapt for the task-level differences conditioned on a graph. Extensive experiments on five real-world graph collections demonstrate the effectiveness of our proposed model.